Conference paper Open Access
Kyriakou Kyriakos;
Barlas Pınar;
Kleanthous Styliani;
Otterbacher Jahna
There are increasing expectations that algorithms should behave in a manner that is socially just. We consider the case of
image tagging APIs and their interpretations of people images. Image taggers have become indispensable in our information
ecosystem, facilitating new modes of visual communication and sharing. Recently, they have become widely available as Cognitive Services. But while tagging APIs offer developers an inexpensive and convenient means to add functionality to their creations, most are opaque and proprietary. Through a cross-platform comparison of six taggers, we show that behaviors differ significantly. While some offer more interpretation on images, they may exhibit less fairness toward the depicted persons, by misuse of gender-related
tags and/or making judgments on a person’s physical appearance. We also discuss the difficulties of studying fairness in situations where algorithmic systems cannot be benchmarkedagainst a ground truth.
Name | Size | |
---|---|---|
ICWSM_tagging.pdf
md5:2e6c32301a60b76c422fcc28f48ba07e |
1.3 MB | Download |
All versions | This version | |
---|---|---|
Views | 43 | 43 |
Downloads | 33 | 33 |
Data volume | 44.4 MB | 44.4 MB |
Unique views | 39 | 39 |
Unique downloads | 31 | 31 |